© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128808
    Prev
    Next
    INDEX
    Explanations

    URLs following guide or product links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     on
    -2.27
     that
    -2.22
    為に
    -1.87
     from
    -1.76
    ところに
    -1.75
    様な
    -1.71
     At
    -1.65
    ほら
    -1.65
     an
    -1.64
    の準備
    -1.64
    POSITIVE LOGITS
    がありますが
    2.42
    そして
    1.96
    ジナル
    1.93
    などを
    1.84
    を
    1.81
    などが
    1.80
    ÚBL
    1.78
    があり
    1.77
    これは
    1.77
    <bos>
    1.75
    Activations Density 0.038%

    No Known Activations